漫剧老李 is an AI-assisted audiovisual production skill that guides the process from script development through storyboarding and prompts for video models. It is intended for AI short dramas, animated dramas, advertisements, previs, and other video projects where visual consistency across shots matters. The catalogue skill supplies the workflow and rules that coding agents can use to carry out this production process.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lixiaoxiao9888-create/manju-laoli-skill --skill sd-jieshuo-enginegit clone --depth 1 https://github.com/lixiaoxiao9888-create/manju-laoli-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-jieshuo-engine)<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-jieshuo-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-jieshuo-engine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-jieshuo-engine"><img src="https://agentmods.dev/badge/skills/lixiaoxiao9888-create/manju-laoli-skill/sd-jieshuo-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00288 | $0.05230 |
| Opus 5.5 | $0.00115 | $0.02092 |
| Sonnet 5.5 | $0.00058 | $0.01046 |
| Haiku 4.5 | $0.00029 | $0.00523 |
Grade A, and why
sd-jieshuo-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sd-jieshuo-engine · 解说叙事类专精引擎（赛道③）
一、角色定位
为赛道③ 解说叙事类（历史事件 / 历史人物介绍 / 科普知识解说）提供完整规则集。它不产出一整套新流程——上游锁系统、投喂格式、机检脚本的权威仍在总控；本引擎负责的是**"解说类怎么用这套流程"的适配口径**。
一句话概括本引擎存在的理由：
解说类的"台词"不是对白，是旁白。 剧情演绎靠"对白 + 表演 + 情节"承载信息；解说叙事靠"旁白/解说词 + 画面注释 + 字幕"承载信息。同一套规则按剧情对白建模，会系统性写错解说类——语速口径错、篇幅卡口误判、分镜单位错、资产约束错位。本引擎的全部规则都从这个前提生长出来。
二、与总控和套装的关系
- 赛道来源：本引擎只在总控〇·0 赛道分流锁选定 ③ 解说类时挂载。赛道未选定时不激活。
- 进入方式：完整流程从总控 short-drama-director 进入；总控锁系统（〇·0 赛道 → 〇·1 素材来源 → A·模型 / B·画幅 / C·交付 / D·段缝）先锁定，再进入剧本层。
- 与其他子技能的关系：
- 与
sd-script-engine是叠加关系（不替代 sd-script-engine）——解说类的"脚本"本质是**旁白稿（VO Script）**而非对白剧本；本引擎定义旁白稿的结构、写作法、与画面的映射，sd-script-engine的「来源登记」纪律照常执行（历史 / 科普题材对信源分级要求尤其高）。 - 与
sd-recon-engine：素材来源锁 ③ 对标 / ④ 热点时照常挂载采风引擎先出《对标情报卡》；历史 / 科普题材的史实与信源纪律由本引擎 §七 强化（T1 史料可直接引用画面，T2 讨论仅作口头转述）。 - 与
sd-asset-engine（资产）/sd-storyboard-engine（分镜）/sd-feed-engine（投喂）/sd-qc-engine（质检）是下游传递关系——场景风格一致 > 人物一致的资产口径、旁白句→画面的分镜口径、C14 配额豁免必须逐阶段传递。
- 与
- 不拥有：锁系统（〇·0/〇·1/A/B/C/D）、七段式投喂格式、H3 格式、资产编号、机检脚本——这些权威都在总控；本引擎只提供"解说类怎么用这些"的适配口径。
三、触发词与进入
触发词：解说、拉片、盘点、逐帧拆解、口播影评、历史人物、历史事件、科普、冷知识、知识区、"一口气看懂"、纪录片解说、口播知识。
用户直接说触发词时，若尚未在完整管线中，先声明一句：
完整制作（资产、分镜、视频）请从总控
short-drama-director进入；赛道请先按总控〇·0 确认（1 国内剧 / 2 海外剧 / 3 解说类 / 4 其他）。本引擎负责解说叙事类的规则集。
进入前提：已确认赛道为 ③ 解说类，且已明确子类型（历史人物志 / 历史事件战役 / 科普知识解说，三选一）。子类型未定时，先停下追问——三类共用一套骨架，但钩子与情绪动线不同（见 §五）。
四、赛道定义：解说叙事类（③）与剧情演绎类（①）的本质差异
| 维度 | ① 国内剧（剧情演绎） | ③ 解说叙事类（本引擎） |
|---|---|---|
| 信息载体 | 对白 + 表演 + 情节 | 旁白/解说词 + 画面注释 + 字幕 |
| 声音结构 | 台词为主（≥70%），VO/OS ≤30%、60~80 字/分钟封顶 | 旁白即主体（80~100%），对白可为零；字数按解说语速单独计 |
| 人物 | 角色连续表演、跨段一致性、FACS 表情 | 可无固定角色；人物以"历史形象/插画形象/影像素材"出现，无需连续表演 |
| 分镜逻辑 | 剧情节拍 → 镜长 | 旁白句 → 画面：一句旁白配 1~2 个画面 |
| 台词字段 | 台词：【角色（语气）："…"】 锁口型 |
解说词走画外 VO，不锁口型；出现对白时（采访/史料引述）才用台词字段 |
| 视觉素材 | 场景资产图 + 角色 4View + 道具 | 时代场景 + 示意图/地图/图文卡 + 插画人物 + 纪实影像（标注） |
| 资产一致性 | 角色跨镜一致是硬约束 | 场景风格一致 > 人物一致；人物可单镜出现 |
| 质量门 | 首镜锚定、摆位必入画、人物账 | 声画信息差检查、旁白句-画面映射、史实/科普正确性、金句结尾 |
| 爆款公式 | 冲突→反转→爽点→情绪闭环 | 钩子→拆解/叙事→揭秘/Wow→升华（详见 §五） |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed 03117259da63
- 4d ago Changed 5fa5422f3eca
- 9d ago First seen · 147 lines · 288 tokens per session scan A 84cfa221856a
sd-jieshuo-engine is a skill published in the GitHub repository lixiaoxiao9888-create/manju-laoli-skill (1,658 stars, last pushed 4d ago), licensed MIT. It adds 288 tokens to every session and 5,230 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.